© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 6980
    Prev
    Next
    INDEX
    Explanations

    body systems diseases parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    leness
    -0.07
     verfolg
    -0.07
    NESS
    -0.07
    èĿł
    -0.07
    noop
    -0.07
    (always
    -0.07
    æIJ¾
    -0.07
    лиÑģ
    -0.07
    à´µàµģà´Ĥ
    -0.06
    ugna
    -0.06
    POSITIVE LOGITS
    åıĹåĪ°å½±åĵį
    0.09
    åı¯èĥ½å¯¼èĩ´
    0.09
     integrity
    0.09
     betroffen
    0.09
    çļĦéĶĻ误
    0.09
    æİĮ管
    0.09
    常è§ģéĹ®é¢ĺ
    0.09
    éĶĻ误æĪĸ
    0.08
    éĥ½æľīåı¯èĥ½
    0.08
     malfunction
    0.08
    Activations Density 0.258%

    No Known Activations